CVE-2024-34359 | llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata

llama-cpp-python is the Python bindings for llama.cpp. `llama-cpp-python` depends on class `Llama` in `llama.py` to load `.gguf` llama.cpp or Latency Machine Learning Models. The `__init__` constructor built in the `Llama` takes several parameters to configure the loading and running of the model. Other than `NUMA, LoRa settings`, `loading tokenizers,` and `hardware settings`, `__init__` also loads the `chat template` from targeted `.gguf` 's Metadata and furtherly parses it to `llama_chat_format.Jinja2ChatFormatter.to_chat_handler()` to construct the `self.chat_handler` for this model. Nevertheless, `Jinja2ChatFormatter` parse the `chat template` within the Metadate with sandbox-less `jinja2.Environment`, which is furthermore rendered in `__call__` to construct the `prompt` of interaction. This allows `jinja2` Server Side Template Injection which leads to remote code execution by a carefully constructed payload.

Published: 2024-05-14 Last update: 2026-04-15 Assigner: [email protected] Source: [email protected]
NVD Status：Deferred，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2024-34359 is rated High Risk (72.3/100): CVSS Critical severity, with high exploitation likelihood (EPSS 61.79%, 98th percentile). EPSS ranks this CVE among the most likely to be exploited in the near term. High exploitation likelihood—assess exposure and prioritize remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2024-34359

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-08 62.31% 61.79% -0.51%
2 2026-05-26 61.79% 62.31% +0.51%
3 2026-05-12 — 61.79% —

Full EPSS history (29 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-34359

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.6 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:C)
Breaking this can reach past the original component and bite other resources—bigger blast radius.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.8 6.0 [email protected]

Weakness enumeration for CVE-2024-34359

GitHub Security Advisory for CVE-2024-34359

GHSA-56xg-wfcc-g829 · Severity: critical · Ecosystem: pip — llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata

Affected software / configurations for CVE-2024-34359

Vendor Product Version Raw CPE
No affected products in dataset.

References for CVE-2024-34359

cvelogic Threat Intelligence